Tight Lower Bounds for Differentially Private Selection
The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
A pervasive task in the differential privacy literature is to select the k items of “highest quality” out of a set of d items, where the quality of each item depends on a sensitive dataset that must be protected. Variants of this task arise naturally in fundamental problems like feature selection and hypothesis testing, and also as subroutines for many sophisticated differentially private algorithms. The standard approaches to these tasks-repeated use of the exponential mechanism or the sparse vector technique-approximately solve this problem given a dataset of n = O(√k log d) samples. We provide a tight lower bound for some very simple variants of the private selection problem. Our lower bound shows that a sample of size n = Ω(√k log d) is required even to achieve a very minimal accuracy guarantee. Our results are based on an extension of the fingerprinting method to sparse selection problems. Previously, the fingerprinting method has been used to provide tight lower bounds for answering an entire set of d queries, but often only some much smaller set of k queries are relevant. Our extension allows us to prove lower bounds that depend on both the number of relevant queries and the total number of queries.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing
Benjamini, Y., & Hochberg, Y. (1995) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1995.tb02031.x · Cited by 109,482
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2014) · Foundations and Trends® in Theoretical Computer Science · doi:10.1561/0400000042 · Cited by 5,557
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
Homer, N., Szelinger, S., Redman, M., Duggan, D., Tembe, W., Muehling, J., Pearson, J. V., Stephan, D. A., Nelson, S. F., & Craig, D. W. (2008) · PLoS Genetics · doi:10.1371/journal.pgen.1000167 · Cited by 1,221 · cited 1×
“Relationship to Previous Lower Bounds and Attacks Our argument is closely related to the work on tracing attacks [29], [30], [16], [17], [18], [26], [31].”
BackgroundBoosting and Differential Privacy
Dwork, C., Rothblum, G. N., & Vadhan, S. (2010) · 2010 IEEE 51st Annual Symposium on Foundations of Computer Science · doi:10.1109/focs.2010.12 · Cited by 784 · cited 1×
“1] for the analysis) to repeatedly “peel off” the column of x with the approximately largest mean x , and applying the composition theorem for differential privacy [12], [42], [43].”
MethodExposed! A Survey of Attacks on Private Data
Dwork, C., Smith, A., Steinke, T., & Ullman, J. (2017) · Annual Review of Statistics and Its Application · doi:10.1146/annurev-statistics-060116-054123 · Cited by 259 · cited 1×
“Relationship to Previous Lower Bounds and Attacks Our argument is closely related to the work on tracing attacks [29], [30], [16], [17], [18], [26], [31].”
BackgroundSelf-citation
Research works printed but not linked: 38
- 10.1007/978-3-642-11799-2_26 · DOI
- 10.1145/1536414.1536465 · DOI
- 10.1007/978-3-540-85174-5_26 · DOI
- 10.1145/1250790.1250804 · DOI · Paper page
- 10.1038/ng.436 · DOI · Paper page
- 10.1145/2488608.2488652 · DOI
- 10.1145/2213977.2214090 · DOI · Paper page
- 10.1137/1.9781611973105.102 · DOI
- 10.1145/1806689.1806795 · DOI · Paper page
- 10.1137/1.9781611973075.90 · DOI
- 10.1145/1806689.1806786 · DOI · Paper page
- 10.1145/2897518.2897566 · DOI · Paper page
- 10.1007/11681878_14 · DOI · Paper page
- 10.1145/773153.773173 · DOI · Paper page
- 10.1007/978-3-540-28628-8_32 · DOI · Paper page
- 10.1145/1065167.1065184 · DOI · Paper page
- 10.1145/2591796.2591877 · DOI
- steinke, 2017, Between pure and approximate differential privacy, Journal of Privacy and Confidentiality, 7, 10.29012/jpc.v7i2.648 · DOI
- 10.1109/FOCS.2015.46 · DOI · Paper page
- 10.1109/FOCS.2007.66 · DOI · Paper page
- 10.1145/2591796.2591883 · DOI · Paper page
- 10.1145/1835804.1835869 · DOI · Paper page
- 10.1109/FOCS.2014.56 · DOI · Paper page
- talwar, 2015, Nearly optimal private lasso, Advances in neural information processing systems, 3025
- 10.1145/1806689.1806794 · DOI · Paper page
- 10.1145/2450142.2450148 · DOI · Paper page
- 10.1007/978-3-642-28914-9_19 · DOI · Paper page
- 10.1109/FOCS.2010.85 · DOI · Paper page
- smith, 2013, Differentially private model selection via stability arguments and the robustness of the lasso, Journal of Machine Learning Research-Proc Track, 30, 819
- 10.1145/2745754.2745755 · DOI
- dwork, 2015, Private false discovery rate control
- 10.1145/1536414.1536467 · DOI · Paper page
- bafna, 2017, The price of selection in differential privacy
- 10.1109/FOCS.2014.55 · DOI · Paper page
- kasiviswanathan, 2014, On the “semantics” of differential privacy: A bayesian formulation, Journal of Privacy and Confidentiality, 6, 10.29012/jpc.v6i1.634 · DOI
- 10.1137/1.9781611974782.85 · DOI
- 10.1007/978-3-662-53641-4_24 · DOI · Paper page
- steinke, 2015, Interactive fingerprinting codes and the hardness of preventing false discovery, Proceedings of The 28th Conference on Learning Theory COLT 2015, 1588
Cited by
Advances and Open Problems in Federated Learning
Kairouz, P., & McMahan, H. B. (2021) · Foundations and Trends in Machine Learning · doi:10.1561/2200000083 · Cited by 7,772
Distributed Differential Privacy via Shuffling
Cheu, A., Smith, A., Ullman, J., Zeber, D., & Zhilyaev, M. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-17653-2_13 · Cited by 268
“In the central model, this problem is solved by the exponential mechanism [24] with a dataset of size just n =O(ε logd), and this is optimal [2, 27].”
BackgroundSelf-citationOn the Power of Multiple Anonymous Messages
Ghazi, B., Golowich, N., Kumar, R., Pagh, R., & Velingker, A. (2019) · arXiv · doi:10.48550/arxiv.1908.11358 · Cited by 26
Metadata
- Authors
- Steinke, T., & Ullman, J.
- Venue
- 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS)
- Publisher
- IEEE
- Published
- 2017-10
- Pages
- 552-563
- ISSN
- 0272-5428 (ISSN-L)
- OpenAlex
- W2608195534
- Cited by
- 48
- References
- 6
- FWCI
- 2.41
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.